{"id":"W2264572084","doi":"10.5539/elt.v9n3p102","title":"Instructional Efficacy of Portfolio for Assessing Iranian EFL Learners’ Speaking Ability","year":2016,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Reflective Practices in Education","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Portfolio; Mathematics education; Test (biology); Population; Control (management); Medical education; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003347111,0.0001006243,0.0001560057,0.00011132,0.0004820494,0.0001021773,0.0002345812,0.0000904746,0.0002055051],"category_scores_gemma":[0.02222824,0.00008272578,0.00009761905,0.0001441095,0.0001926295,0.001303157,0.00003495074,0.0002402982,0.000003058467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003364942,"about_ca_system_score_gemma":0.0002133214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001066229,"about_ca_topic_score_gemma":0.0001937587,"domain_scores_codex":[0.998259,0.0005810428,0.0002673292,0.0002797609,0.0003396787,0.0002731858],"domain_scores_gemma":[0.9975026,0.001767122,0.0003147017,0.0002198951,0.0001230309,0.00007264809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002818151,0.0001288682,0.03591627,0.00002183822,0.00002949941,0.000001013513,0.3686872,0.00001020035,0.01258004,0.01693137,0.00004016507,0.5656254],"study_design_scores_gemma":[0.003004645,0.0001148072,0.107899,0.0004870072,0.0001500139,0.000006414771,0.7694407,0.00005169663,0.005705821,0.006087321,0.1061763,0.0008763769],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8798934,0.00004624886,0.005085651,0.0002496896,0.001205707,0.0002453562,0.000004166828,0.000111694,0.1131581],"genre_scores_gemma":[0.9756321,0.000003703281,0.02227001,0.00002683615,0.001777322,0.00001211597,0.000004108676,0.00001834639,0.0002554067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.564749,"threshold_uncertainty_score":0.9860079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02629685041682688,"score_gpt":0.3913931459463184,"score_spread":0.3650962955294915,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}